print.py

print("Hello World!")

import docx2txt
from PyPDF2 import PdfFileReader, PdfFileWriter, PdfFileMerger

# Extracting text from DOCX
def doctotext(m):
    temp = docx2txt.process(m)
    resume_text = [line.replace('\t', ' ') for line in temp.split('\n') if line]
    text = ' '.join(resume_text)
    return (text)
    
#Extracting text from PDF
def pdftotext(m):
    # pdf file object
    # you can find find the pdf file with complete code in below
    pdfFileObj = open(m, 'rb')

    # pdf reader object
    pdfFileReader = PdfFileReader(pdfFileObj)

    # number of pages in pdf
    num_pages = pdfFileReader.numPages

    currentPageNumber = 0
    text = ''
    print(pdfFileReader.getFields())
    # Loop in all the pdf pages.
    while(currentPageNumber < num_pages ):

        # Get the specified pdf page object.
        pdfPage = pdfFileReader.getPage(currentPageNumber)
        # Get pdf page text.
        text = text + pdfPage.extractText()

        # Process next page.
        currentPageNumber += 1
    return (text)

#main function
if __name__ == '__main__': 

    FilePath = 'AI.pdf'
    FilePath.lower().endswith(('.png', '.docx'))
    if FilePath.endswith('.docx'):
      textinput = doctotext(FilePath) 
    elif FilePath.endswith('.pdf'):
      textinput = pdftotext('Sample.pdf')
    else:
      print("File not support")
    print(textinput[0:10])


import spacy
import en_core_web_sm
from spacy.matcher import Matcher

# load pre-trained model
nlp = en_core_web_sm.load()

# initialize matcher with a vocab
matcher = Matcher(nlp.vocab)


def extract_name(resume_text):
    nlp_text = nlp(resume_text)
    
    # First name and Last name are always Proper Nouns
    pattern = [{'POS': 'PROPN'}, {'POS': 'PROPN'}]
    
    matcher.add('NAME', [pattern])
    
    matches = matcher(nlp_text)
    print(type(matches))
    for x in range(len(matches)):
        print(matches[x])
    for match_id, start, end in matches:
        # print(start,end,match_id)
        # print(nlp_text)
        span = nlp_text[start:end]
        print(span)
        return span.text
print('Name: ',extract_name(textinput))


import re
from nltk.corpus import stopwords


# Grad all general stop words
STOPWORDS = set(stopwords.words('english'))

# Education Degrees
EDUCATION = [
            'BE','B.E.', 'B.E', 'BS', 'B.S', 
            'ME', 'M.E', 'M.E.', 'M.B.A', 'MBA', 'MS', 'M.S', 
            'BTECH', 'B.TECH', 'M.TECH', 'MTECH', 
            'SSLC', 'SSC' 'HSC', 'CBSE', 'ICSE', 'X', 'XII'
        ]

def extract_education(resume_text):
    nlp_text = nlp(resume_text)

    # Sentence Tokenizer
    nlp_text = [str(sent).strip() for sent in nlp_text.sents]

    edu = {}
    # Extract education degree
    for index, text in enumerate(nlp_text):
        for tex in text.split():
            # Replace all special symbols
            tex = re.sub(r'[?|$|.|!|,]', r'', tex)
            if tex.upper() in EDUCATION and tex not in STOPWORDS:
                edu[tex] = text + nlp_text[index]
                
                

    # Extract year
    education = []
    for key in edu.keys():
        year = re.search(re.compile(r'(((20|19)(\d{})))'), edu[key])
        if year:
            education.append((key, ''.join(year[0])))
        else:
            education.append(key)
    return education
print('Qualification: ',extract_education(textinput))
import pandas as pd
import spacy
nlp = spacy.load('en_core_web_sm')

def extract_skills(resume_text):
    nlp_text = nlp(resume_text)

    # removing stop words and implementing word tokenization
    tokens = [token.text for token in nlp_text if not token.is_stop]
  
    
    # extract values
    skills = ['JavaScript','SQL']
    print(skills)
    skillset = []
    
    # check for one-grams (example: python)
    for token in tokens:
        if token in skills:
            skillset.append(token)
    return skillset
    
print ('Skills',extract_skills(textinput))